let TargetPrefix = "aarch64" in { // All intrinsics start with "llvm.aarch64.".
+
+class AdvSIMD_Pred2VectorArg_Intrinsic
+ : Intrinsic<[llvm_anyvector_ty],
+ [LLVMScalarOrSameVectorWidth<0, llvm_i1_ty>, LLVMMatchType<0>, LLVMMatchType<0>],
+ [IntrNoMem]>;
+
+
//
// Integer arithmetic
//
+def int_aarch64_sve_add : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_sub : AdvSIMD_Pred2VectorArg_Intrinsic;
+def int_aarch64_sve_subr : AdvSIMD_Pred2VectorArg_Intrinsic;
+
+def int_aarch64_sve_bic : AdvSIMD_2VectorArg_Intrinsic;
+
def int_aarch64_sve_abs : AdvSIMD_Merged1VectorArg_Intrinsic;
def int_aarch64_sve_neg : AdvSIMD_Merged1VectorArg_Intrinsic;
addRegisterClass(MVT::nxv4f32, &AArch64::ZPRRegClass);
addRegisterClass(MVT::nxv1f64, &AArch64::ZPRRegClass);
addRegisterClass(MVT::nxv2f64, &AArch64::ZPRRegClass);
+
+ for (auto VT : { MVT::nxv16i8, MVT::nxv8i16, MVT::nxv4i32, MVT::nxv2i64 }) {
+ setOperationAction(ISD::SADDSAT, VT, Legal);
+ setOperationAction(ISD::UADDSAT, VT, Legal);
+ setOperationAction(ISD::SSUBSAT, VT, Legal);
+ setOperationAction(ISD::USUBSAT, VT, Legal);
+ }
}
// Compute derived properties from the register classes
def SETFFR : sve_int_setffr<"setffr">;
def WRFFR : sve_int_wrffr<"wrffr">;
- defm ADD_ZZZ : sve_int_bin_cons_arit_0<0b000, "add">;
- defm SUB_ZZZ : sve_int_bin_cons_arit_0<0b001, "sub">;
- defm SQADD_ZZZ : sve_int_bin_cons_arit_0<0b100, "sqadd">;
- defm UQADD_ZZZ : sve_int_bin_cons_arit_0<0b101, "uqadd">;
- defm SQSUB_ZZZ : sve_int_bin_cons_arit_0<0b110, "sqsub">;
- defm UQSUB_ZZZ : sve_int_bin_cons_arit_0<0b111, "uqsub">;
-
- defm AND_ZZZ : sve_int_bin_cons_log<0b00, "and">;
- defm ORR_ZZZ : sve_int_bin_cons_log<0b01, "orr">;
- defm EOR_ZZZ : sve_int_bin_cons_log<0b10, "eor">;
- defm BIC_ZZZ : sve_int_bin_cons_log<0b11, "bic">;
-
- defm ADD_ZPmZ : sve_int_bin_pred_arit_0<0b000, "add">;
- defm SUB_ZPmZ : sve_int_bin_pred_arit_0<0b001, "sub">;
- defm SUBR_ZPmZ : sve_int_bin_pred_arit_0<0b011, "subr">;
-
- defm ORR_ZPmZ : sve_int_bin_pred_log<0b000, "orr">;
- defm EOR_ZPmZ : sve_int_bin_pred_log<0b001, "eor">;
- defm AND_ZPmZ : sve_int_bin_pred_log<0b010, "and">;
- defm BIC_ZPmZ : sve_int_bin_pred_log<0b011, "bic">;
+ defm ADD_ZZZ : sve_int_bin_cons_arit_0<0b000, "add", add>;
+ defm SUB_ZZZ : sve_int_bin_cons_arit_0<0b001, "sub", sub>;
+ defm SQADD_ZZZ : sve_int_bin_cons_arit_0<0b100, "sqadd", saddsat>;
+ defm UQADD_ZZZ : sve_int_bin_cons_arit_0<0b101, "uqadd", uaddsat>;
+ defm SQSUB_ZZZ : sve_int_bin_cons_arit_0<0b110, "sqsub", ssubsat>;
+ defm UQSUB_ZZZ : sve_int_bin_cons_arit_0<0b111, "uqsub", usubsat>;
+
+ defm AND_ZZZ : sve_int_bin_cons_log<0b00, "and", and>;
+ defm ORR_ZZZ : sve_int_bin_cons_log<0b01, "orr", or>;
+ defm EOR_ZZZ : sve_int_bin_cons_log<0b10, "eor", xor>;
+ defm BIC_ZZZ : sve_int_bin_cons_log<0b11, "bic", int_aarch64_sve_bic>;
+
+ defm ADD_ZPmZ : sve_int_bin_pred_arit_0<0b000, "add", int_aarch64_sve_add>;
+ defm SUB_ZPmZ : sve_int_bin_pred_arit_0<0b001, "sub", int_aarch64_sve_sub>;
+ defm SUBR_ZPmZ : sve_int_bin_pred_arit_0<0b011, "subr", int_aarch64_sve_subr>;
+
+ defm ORR_ZPmZ : sve_int_bin_pred_log<0b000, "orr", null_frag>;
+ defm EOR_ZPmZ : sve_int_bin_pred_log<0b001, "eor", null_frag>;
+ defm AND_ZPmZ : sve_int_bin_pred_log<0b010, "and", null_frag>;
+ defm BIC_ZPmZ : sve_int_bin_pred_log<0b011, "bic", null_frag>;
defm ADD_ZI : sve_int_arith_imm0<0b000, "add">;
defm SUB_ZI : sve_int_arith_imm0<0b001, "sub">;
defm UMIN_ZI : sve_int_arith_imm1<0b11, "umin", imm0_255>;
defm MUL_ZI : sve_int_arith_imm2<"mul">;
- defm MUL_ZPmZ : sve_int_bin_pred_arit_2<0b000, "mul">;
- defm SMULH_ZPmZ : sve_int_bin_pred_arit_2<0b010, "smulh">;
- defm UMULH_ZPmZ : sve_int_bin_pred_arit_2<0b011, "umulh">;
+ defm MUL_ZPmZ : sve_int_bin_pred_arit_2<0b000, "mul", null_frag>;
+ defm SMULH_ZPmZ : sve_int_bin_pred_arit_2<0b010, "smulh", null_frag>;
+ defm UMULH_ZPmZ : sve_int_bin_pred_arit_2<0b011, "umulh", null_frag>;
- defm SDIV_ZPmZ : sve_int_bin_pred_arit_2_div<0b100, "sdiv">;
- defm UDIV_ZPmZ : sve_int_bin_pred_arit_2_div<0b101, "udiv">;
- defm SDIVR_ZPmZ : sve_int_bin_pred_arit_2_div<0b110, "sdivr">;
- defm UDIVR_ZPmZ : sve_int_bin_pred_arit_2_div<0b111, "udivr">;
+ defm SDIV_ZPmZ : sve_int_bin_pred_arit_2_div<0b100, "sdiv", null_frag>;
+ defm UDIV_ZPmZ : sve_int_bin_pred_arit_2_div<0b101, "udiv", null_frag>;
+ defm SDIVR_ZPmZ : sve_int_bin_pred_arit_2_div<0b110, "sdivr", null_frag>;
+ defm UDIVR_ZPmZ : sve_int_bin_pred_arit_2_div<0b111, "udivr", null_frag>;
defm SDOT_ZZZ : sve_intx_dot<0b0, "sdot", int_aarch64_sve_sdot>;
defm UDOT_ZZZ : sve_intx_dot<0b1, "udot", int_aarch64_sve_udot>;
defm FABS_ZPmZ : sve_int_un_pred_arit_1_fp<0b100, "fabs">;
defm FNEG_ZPmZ : sve_int_un_pred_arit_1_fp<0b101, "fneg">;
- defm SMAX_ZPmZ : sve_int_bin_pred_arit_1<0b000, "smax">;
- defm UMAX_ZPmZ : sve_int_bin_pred_arit_1<0b001, "umax">;
- defm SMIN_ZPmZ : sve_int_bin_pred_arit_1<0b010, "smin">;
- defm UMIN_ZPmZ : sve_int_bin_pred_arit_1<0b011, "umin">;
- defm SABD_ZPmZ : sve_int_bin_pred_arit_1<0b100, "sabd">;
- defm UABD_ZPmZ : sve_int_bin_pred_arit_1<0b101, "uabd">;
+ defm SMAX_ZPmZ : sve_int_bin_pred_arit_1<0b000, "smax", null_frag>;
+ defm UMAX_ZPmZ : sve_int_bin_pred_arit_1<0b001, "umax", null_frag>;
+ defm SMIN_ZPmZ : sve_int_bin_pred_arit_1<0b010, "smin", null_frag>;
+ defm UMIN_ZPmZ : sve_int_bin_pred_arit_1<0b011, "umin", null_frag>;
+ defm SABD_ZPmZ : sve_int_bin_pred_arit_1<0b100, "sabd", null_frag>;
+ defm UABD_ZPmZ : sve_int_bin_pred_arit_1<0b101, "uabd", null_frag>;
defm FRECPE_ZZ : sve_fp_2op_u_zd<0b110, "frecpe">;
defm FRSQRTE_ZZ : sve_fp_2op_u_zd<0b111, "frsqrte">;
: Pat<(vtd (op vt1:$Op1)),
(inst $Op1)>;
+class SVE_2_Op_Pat<ValueType vtd, SDPatternOperator op, ValueType vt1,
+ ValueType vt2, Instruction inst>
+: Pat<(vtd (op vt1:$Op1, vt2:$Op2)),
+ (inst $Op1, $Op2)>;
+
class SVE_3_Op_Pat<ValueType vtd, SDPatternOperator op, ValueType vt1,
ValueType vt2, ValueType vt3, Instruction inst>
: Pat<(vtd (op vt1:$Op1, vt2:$Op2, vt3:$Op3)),
let Inst{4-0} = Zd;
}
-multiclass sve_int_bin_cons_arit_0<bits<3> opc, string asm> {
+multiclass sve_int_bin_cons_arit_0<bits<3> opc, string asm, SDPatternOperator op> {
def _B : sve_int_bin_cons_arit_0<0b00, opc, asm, ZPR8>;
def _H : sve_int_bin_cons_arit_0<0b01, opc, asm, ZPR16>;
def _S : sve_int_bin_cons_arit_0<0b10, opc, asm, ZPR32>;
def _D : sve_int_bin_cons_arit_0<0b11, opc, asm, ZPR64>;
+
+ def : SVE_2_Op_Pat<nxv16i8, op, nxv16i8, nxv16i8, !cast<Instruction>(NAME # _B)>;
+ def : SVE_2_Op_Pat<nxv8i16, op, nxv8i16, nxv8i16, !cast<Instruction>(NAME # _H)>;
+ def : SVE_2_Op_Pat<nxv4i32, op, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>;
+ def : SVE_2_Op_Pat<nxv2i64, op, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>;
}
//===----------------------------------------------------------------------===//
let ElementSize = zprty.ElementSize;
}
-multiclass sve_int_bin_pred_log<bits<3> opc, string asm> {
+multiclass sve_int_bin_pred_log<bits<3> opc, string asm, SDPatternOperator op> {
def _B : sve_int_bin_pred_arit_log<0b00, 0b11, opc, asm, ZPR8>;
def _H : sve_int_bin_pred_arit_log<0b01, 0b11, opc, asm, ZPR16>;
def _S : sve_int_bin_pred_arit_log<0b10, 0b11, opc, asm, ZPR32>;
def _D : sve_int_bin_pred_arit_log<0b11, 0b11, opc, asm, ZPR64>;
+
+ def : SVE_3_Op_Pat<nxv16i8, op, nxv16i1, nxv16i8, nxv16i8, !cast<Instruction>(NAME # _B)>;
+ def : SVE_3_Op_Pat<nxv8i16, op, nxv8i1, nxv8i16, nxv8i16, !cast<Instruction>(NAME # _H)>;
+ def : SVE_3_Op_Pat<nxv4i32, op, nxv4i1, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>;
+ def : SVE_3_Op_Pat<nxv2i64, op, nxv2i1, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>;
}
-multiclass sve_int_bin_pred_arit_0<bits<3> opc, string asm> {
+multiclass sve_int_bin_pred_arit_0<bits<3> opc, string asm, SDPatternOperator op> {
def _B : sve_int_bin_pred_arit_log<0b00, 0b00, opc, asm, ZPR8>;
def _H : sve_int_bin_pred_arit_log<0b01, 0b00, opc, asm, ZPR16>;
def _S : sve_int_bin_pred_arit_log<0b10, 0b00, opc, asm, ZPR32>;
def _D : sve_int_bin_pred_arit_log<0b11, 0b00, opc, asm, ZPR64>;
+
+ def : SVE_3_Op_Pat<nxv16i8, op, nxv16i1, nxv16i8, nxv16i8, !cast<Instruction>(NAME # _B)>;
+ def : SVE_3_Op_Pat<nxv8i16, op, nxv8i1, nxv8i16, nxv8i16, !cast<Instruction>(NAME # _H)>;
+ def : SVE_3_Op_Pat<nxv4i32, op, nxv4i1, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>;
+ def : SVE_3_Op_Pat<nxv2i64, op, nxv2i1, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>;
}
-multiclass sve_int_bin_pred_arit_1<bits<3> opc, string asm> {
+multiclass sve_int_bin_pred_arit_1<bits<3> opc, string asm, SDPatternOperator op> {
def _B : sve_int_bin_pred_arit_log<0b00, 0b01, opc, asm, ZPR8>;
def _H : sve_int_bin_pred_arit_log<0b01, 0b01, opc, asm, ZPR16>;
def _S : sve_int_bin_pred_arit_log<0b10, 0b01, opc, asm, ZPR32>;
def _D : sve_int_bin_pred_arit_log<0b11, 0b01, opc, asm, ZPR64>;
+
+ def : SVE_3_Op_Pat<nxv16i8, op, nxv16i1, nxv16i8, nxv16i8, !cast<Instruction>(NAME # _B)>;
+ def : SVE_3_Op_Pat<nxv8i16, op, nxv8i1, nxv8i16, nxv8i16, !cast<Instruction>(NAME # _H)>;
+ def : SVE_3_Op_Pat<nxv4i32, op, nxv4i1, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>;
+ def : SVE_3_Op_Pat<nxv2i64, op, nxv2i1, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>;
}
-multiclass sve_int_bin_pred_arit_2<bits<3> opc, string asm> {
+multiclass sve_int_bin_pred_arit_2<bits<3> opc, string asm, SDPatternOperator op> {
def _B : sve_int_bin_pred_arit_log<0b00, 0b10, opc, asm, ZPR8>;
def _H : sve_int_bin_pred_arit_log<0b01, 0b10, opc, asm, ZPR16>;
def _S : sve_int_bin_pred_arit_log<0b10, 0b10, opc, asm, ZPR32>;
def _D : sve_int_bin_pred_arit_log<0b11, 0b10, opc, asm, ZPR64>;
+
+ def : SVE_3_Op_Pat<nxv16i8, op, nxv16i1, nxv16i8, nxv16i8, !cast<Instruction>(NAME # _B)>;
+ def : SVE_3_Op_Pat<nxv8i16, op, nxv8i1, nxv8i16, nxv8i16, !cast<Instruction>(NAME # _H)>;
+ def : SVE_3_Op_Pat<nxv4i32, op, nxv4i1, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>;
+ def : SVE_3_Op_Pat<nxv2i64, op, nxv2i1, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>;
}
// Special case for divides which are not defined for 8b/16b elements.
-multiclass sve_int_bin_pred_arit_2_div<bits<3> opc, string asm> {
+multiclass sve_int_bin_pred_arit_2_div<bits<3> opc, string asm, SDPatternOperator op> {
def _S : sve_int_bin_pred_arit_log<0b10, 0b10, opc, asm, ZPR32>;
def _D : sve_int_bin_pred_arit_log<0b11, 0b10, opc, asm, ZPR64>;
+
+ def : SVE_3_Op_Pat<nxv4i32, op, nxv4i1, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>;
+ def : SVE_3_Op_Pat<nxv2i64, op, nxv2i1, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>;
}
//===----------------------------------------------------------------------===//
let Inst{4-0} = Zd;
}
-multiclass sve_int_bin_cons_log<bits<2> opc, string asm> {
+multiclass sve_int_bin_cons_log<bits<2> opc, string asm, SDPatternOperator op> {
def NAME : sve_int_bin_cons_log<opc, asm>;
+ def : SVE_2_Op_Pat<nxv16i8, op, nxv16i8, nxv16i8, !cast<Instruction>(NAME)>;
+ def : SVE_2_Op_Pat<nxv8i16, op, nxv8i16, nxv8i16, !cast<Instruction>(NAME)>;
+ def : SVE_2_Op_Pat<nxv4i32, op, nxv4i32, nxv4i32, !cast<Instruction>(NAME)>;
+ def : SVE_2_Op_Pat<nxv2i64, op, nxv2i64, nxv2i64, !cast<Instruction>(NAME)>;
+
def : InstAlias<asm # "\t$Zd, $Zn, $Zm",
(!cast<Instruction>(NAME) ZPR8:$Zd, ZPR8:$Zn, ZPR8:$Zm), 1>;
def : InstAlias<asm # "\t$Zd, $Zn, $Zm",
--- /dev/null
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
+
+define <vscale x 16 x i8> @add_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: add_i8:
+; CHECK: add z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT: ret
+ %out = call <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1> %pg,
+ <vscale x 16 x i8> %a,
+ <vscale x 16 x i8> %b)
+ ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @add_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: add_i16:
+; CHECK: add z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+ %out = call <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1> %pg,
+ <vscale x 8 x i16> %a,
+ <vscale x 8 x i16> %b)
+ ret <vscale x 8 x i16> %out
+}
+
+define <vscale x 4 x i32> @add_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: add_i32:
+; CHECK: add z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+ %out = call <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1> %pg,
+ <vscale x 4 x i32> %a,
+ <vscale x 4 x i32> %b)
+ ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @add_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: add_i64:
+; CHECK: add z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+ %out = call <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1> %pg,
+ <vscale x 2 x i64> %a,
+ <vscale x 2 x i64> %b)
+ ret <vscale x 2 x i64> %out
+}
+
+
+
+
+define <vscale x 16 x i8> @sub_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: sub_i8:
+; CHECK: sub z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT: ret
+ %out = call <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1> %pg,
+ <vscale x 16 x i8> %a,
+ <vscale x 16 x i8> %b)
+ ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @sub_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: sub_i16:
+; CHECK: sub z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+ %out = call <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1> %pg,
+ <vscale x 8 x i16> %a,
+ <vscale x 8 x i16> %b)
+ ret <vscale x 8 x i16> %out
+}
+
+define <vscale x 4 x i32> @sub_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: sub_i32:
+; CHECK: sub z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+ %out = call <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1> %pg,
+ <vscale x 4 x i32> %a,
+ <vscale x 4 x i32> %b)
+ ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @sub_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: sub_i64:
+; CHECK: sub z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+ %out = call <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1> %pg,
+ <vscale x 2 x i64> %a,
+ <vscale x 2 x i64> %b)
+ ret <vscale x 2 x i64> %out
+}
+
+
+
+define <vscale x 16 x i8> @subr_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: subr_i8:
+; CHECK: subr z0.b, p0/m, z0.b, z1.b
+; CHECK-NEXT: ret
+ %out = call <vscale x 16 x i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1> %pg,
+ <vscale x 16 x i8> %a,
+ <vscale x 16 x i8> %b)
+ ret <vscale x 16 x i8> %out
+}
+
+define <vscale x 8 x i16> @subr_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: subr_i16:
+; CHECK: subr z0.h, p0/m, z0.h, z1.h
+; CHECK-NEXT: ret
+ %out = call <vscale x 8 x i16> @llvm.aarch64.sve.subr.nxv8i16(<vscale x 8 x i1> %pg,
+ <vscale x 8 x i16> %a,
+ <vscale x 8 x i16> %b)
+ ret <vscale x 8 x i16> %out
+}
+
+define <vscale x 4 x i32> @subr_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: subr_i32:
+; CHECK: subr z0.s, p0/m, z0.s, z1.s
+; CHECK-NEXT: ret
+ %out = call <vscale x 4 x i32> @llvm.aarch64.sve.subr.nxv4i32(<vscale x 4 x i1> %pg,
+ <vscale x 4 x i32> %a,
+ <vscale x 4 x i32> %b)
+ ret <vscale x 4 x i32> %out
+}
+
+define <vscale x 2 x i64> @subr_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: subr_i64:
+; CHECK: subr z0.d, p0/m, z0.d, z1.d
+; CHECK-NEXT: ret
+ %out = call <vscale x 2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x 2 x i1> %pg,
+ <vscale x 2 x i64> %a,
+ <vscale x 2 x i64> %b)
+ ret <vscale x 2 x i64> %out
+}
+
+
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.add.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+declare <vscale x 8 x i16> @llvm.aarch64.sve.add.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.add.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.add.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.sub.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+declare <vscale x 8 x i16> @llvm.aarch64.sve.sub.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.sub.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.sub.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
+
+declare <vscale x 16 x i8> @llvm.aarch64.sve.subr.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
+declare <vscale x 8 x i16> @llvm.aarch64.sve.subr.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.subr.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 2 x i64> @llvm.aarch64.sve.subr.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
--- /dev/null
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
+
+define <vscale x 2 x i64> @add_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: add_i64
+; CHECK: add z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = add <vscale x 2 x i64> %a, %b
+ ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @add_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: add_i32
+; CHECK: add z0.s, z0.s, z1.s
+; CHECK-NEXT: ret
+ %res = add <vscale x 4 x i32> %a, %b
+ ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @add_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: add_i16
+; CHECK: add z0.h, z0.h, z1.h
+; CHECK-NEXT: ret
+ %res = add <vscale x 8 x i16> %a, %b
+ ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @add_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: add_i8
+; CHECK: add z0.b, z0.b, z1.b
+; CHECK-NEXT: ret
+ %res = add <vscale x 16 x i8> %a, %b
+ ret <vscale x 16 x i8> %res
+}
+
+define <vscale x 2 x i64> @sub_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: sub_i64
+; CHECK: sub z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = sub <vscale x 2 x i64> %a, %b
+ ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @sub_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: sub_i32
+; CHECK: sub z0.s, z0.s, z1.s
+; CHECK-NEXT: ret
+ %res = sub <vscale x 4 x i32> %a, %b
+ ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @sub_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: sub_i16
+; CHECK: sub z0.h, z0.h, z1.h
+; CHECK-NEXT: ret
+ %res = sub <vscale x 8 x i16> %a, %b
+ ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @sub_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: sub_i8
+; CHECK: sub z0.b, z0.b, z1.b
+; CHECK-NEXT: ret
+ %res = sub <vscale x 16 x i8> %a, %b
+ ret <vscale x 16 x i8> %res
+}
+
+define <vscale x 2 x i64> @sqadd_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: sqadd_i64
+; CHECK: sqadd z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = call <vscale x 2 x i64> @llvm.sadd.sat.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+ ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @sqadd_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: sqadd_i32
+; CHECK: sqadd z0.s, z0.s, z1.s
+; CHECK-NEXT: ret
+ %res = call <vscale x 4 x i32> @llvm.sadd.sat.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+ ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @sqadd_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: sqadd_i16
+; CHECK: sqadd z0.h, z0.h, z1.h
+; CHECK-NEXT: ret
+ %res = call <vscale x 8 x i16> @llvm.sadd.sat.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+ ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @sqadd_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: sqadd_i8
+; CHECK: sqadd z0.b, z0.b, z1.b
+; CHECK-NEXT: ret
+ %res = call <vscale x 16 x i8> @llvm.sadd.sat.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+ ret <vscale x 16 x i8> %res
+}
+
+
+define <vscale x 2 x i64> @sqsub_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: sqsub_i64
+; CHECK: sqsub z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = call <vscale x 2 x i64> @llvm.ssub.sat.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+ ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @sqsub_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: sqsub_i32
+; CHECK: sqsub z0.s, z0.s, z1.s
+; CHECK-NEXT: ret
+ %res = call <vscale x 4 x i32> @llvm.ssub.sat.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+ ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @sqsub_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: sqsub_i16
+; CHECK: sqsub z0.h, z0.h, z1.h
+; CHECK-NEXT: ret
+ %res = call <vscale x 8 x i16> @llvm.ssub.sat.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+ ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @sqsub_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: sqsub_i8
+; CHECK: sqsub z0.b, z0.b, z1.b
+; CHECK-NEXT: ret
+ %res = call <vscale x 16 x i8> @llvm.ssub.sat.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+ ret <vscale x 16 x i8> %res
+}
+
+
+define <vscale x 2 x i64> @uqadd_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: uqadd_i64
+; CHECK: uqadd z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = call <vscale x 2 x i64> @llvm.uadd.sat.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+ ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @uqadd_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: uqadd_i32
+; CHECK: uqadd z0.s, z0.s, z1.s
+; CHECK-NEXT: ret
+ %res = call <vscale x 4 x i32> @llvm.uadd.sat.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+ ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @uqadd_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: uqadd_i16
+; CHECK: uqadd z0.h, z0.h, z1.h
+; CHECK-NEXT: ret
+ %res = call <vscale x 8 x i16> @llvm.uadd.sat.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+ ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @uqadd_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: uqadd_i8
+; CHECK: uqadd z0.b, z0.b, z1.b
+; CHECK-NEXT: ret
+ %res = call <vscale x 16 x i8> @llvm.uadd.sat.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+ ret <vscale x 16 x i8> %res
+}
+
+
+define <vscale x 2 x i64> @uqsub_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: uqsub_i64
+; CHECK: uqsub z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = call <vscale x 2 x i64> @llvm.usub.sat.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
+ ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @uqsub_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: uqsub_i32
+; CHECK: uqsub z0.s, z0.s, z1.s
+; CHECK-NEXT: ret
+ %res = call <vscale x 4 x i32> @llvm.usub.sat.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
+ ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @uqsub_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: uqsub_i16
+; CHECK: uqsub z0.h, z0.h, z1.h
+; CHECK-NEXT: ret
+ %res = call <vscale x 8 x i16> @llvm.usub.sat.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
+ ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @uqsub_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: uqsub_i8
+; CHECK: uqsub z0.b, z0.b, z1.b
+; CHECK-NEXT: ret
+ %res = call <vscale x 16 x i8> @llvm.usub.sat.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
+ ret <vscale x 16 x i8> %res
+}
+
+declare <vscale x 16 x i8> @llvm.sadd.sat.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
+declare <vscale x 8 x i16> @llvm.sadd.sat.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
+declare <vscale x 4 x i32> @llvm.sadd.sat.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 2 x i64> @llvm.sadd.sat.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
+
+declare <vscale x 16 x i8> @llvm.ssub.sat.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
+declare <vscale x 8 x i16> @llvm.ssub.sat.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
+declare <vscale x 4 x i32> @llvm.ssub.sat.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 2 x i64> @llvm.ssub.sat.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
+
+declare <vscale x 16 x i8> @llvm.uadd.sat.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
+declare <vscale x 8 x i16> @llvm.uadd.sat.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
+declare <vscale x 4 x i32> @llvm.uadd.sat.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 2 x i64> @llvm.uadd.sat.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
+
+declare <vscale x 16 x i8> @llvm.usub.sat.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
+declare <vscale x 8 x i16> @llvm.usub.sat.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
+declare <vscale x 4 x i32> @llvm.usub.sat.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 2 x i64> @llvm.usub.sat.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
--- /dev/null
+; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
+
+define <vscale x 2 x i64> @and_d(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: and_d
+; CHECK: and z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = and <vscale x 2 x i64> %a, %b
+ ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @and_s(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: and_s
+; CHECK: and z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = and <vscale x 4 x i32> %a, %b
+ ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @and_h(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: and_h
+; CHECK: and z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = and <vscale x 8 x i16> %a, %b
+ ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @and_b(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: and_b
+; CHECK: and z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = and <vscale x 16 x i8> %a, %b
+ ret <vscale x 16 x i8> %res
+}
+define <vscale x 2 x i64> @or_d(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: or_d
+; CHECK: orr z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = or <vscale x 2 x i64> %a, %b
+ ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @or_s(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: or_s
+; CHECK: orr z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = or <vscale x 4 x i32> %a, %b
+ ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @or_h(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: or_h
+; CHECK: orr z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = or <vscale x 8 x i16> %a, %b
+ ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @or_b(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: or_b
+; CHECK: orr z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = or <vscale x 16 x i8> %a, %b
+ ret <vscale x 16 x i8> %res
+}
+
+define <vscale x 2 x i64> @xor_d(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: xor_d
+; CHECK: eor z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = xor <vscale x 2 x i64> %a, %b
+ ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @xor_s(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: xor_s
+; CHECK: eor z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = xor <vscale x 4 x i32> %a, %b
+ ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @xor_h(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: xor_h
+; CHECK: eor z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = xor <vscale x 8 x i16> %a, %b
+ ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @xor_b(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: xor_b
+; CHECK: eor z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = xor <vscale x 16 x i8> %a, %b
+ ret <vscale x 16 x i8> %res
+}
+
+define <vscale x 2 x i64> @bic_d(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
+; CHECK-LABEL: bic_d
+; CHECK: bic z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = call <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i64> %a,
+ <vscale x 2 x i64> %b)
+ ret <vscale x 2 x i64> %res
+}
+
+define <vscale x 4 x i32> @bic_s(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
+; CHECK-LABEL: bic_s
+; CHECK: bic z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = call <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i32> %a,
+ <vscale x 4 x i32> %b)
+ ret <vscale x 4 x i32> %res
+}
+
+define <vscale x 8 x i16> @bic_h(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
+; CHECK-LABEL: bic_h
+; CHECK: bic z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = call <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i16> %a,
+ <vscale x 8 x i16> %b)
+
+ ret <vscale x 8 x i16> %res
+}
+
+define <vscale x 16 x i8> @bic_b(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
+; CHECK-LABEL: bic_b
+; CHECK: bic z0.d, z0.d, z1.d
+; CHECK-NEXT: ret
+ %res = call <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i8> %a,
+ <vscale x 16 x i8> %b)
+ ret <vscale x 16 x i8> %res
+}
+
+declare <vscale x 2 x i64> @llvm.aarch64.sve.bic.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
+declare <vscale x 4 x i32> @llvm.aarch64.sve.bic.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
+declare <vscale x 8 x i16> @llvm.aarch64.sve.bic.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
+declare <vscale x 16 x i8> @llvm.aarch64.sve.bic.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)